Charging control method and device, equipment, storage medium and program product

Abstract

The embodiment of the invention provides a charging control method and device, equipment, a storage medium and a program product. Firstly, a personalized user portrait is constructed based on historical data, and meanwhile, real-time operation parameters of a target battery are collected; and generating a personalized charging strategy based on the user portrait and the instant state data, thereby dynamically adjusting current, voltage and time parameters in the charging process based on the charging strategy. In the scheme, deep fusion of the charging strategy and the user behavior can be realized, the service life of the battery is prolonged while the satisfaction degree of the user is improved, and the long-term use cost is reduced.

Description

Technical Field

[0001] This application relates to the field of equipment safety, and more particularly to a charging control method, apparatus, device, storage medium, and program product. Background Technology

[0002] In the field of battery energy storage, the charging strategy of the Battery Management System (BMS) is one of the core technologies, and its quality directly affects the battery's lifespan, system operating efficiency, and electricity costs. The charging process not only needs to meet the user's demand for charging speed, but also must take into account the battery's own health status to prevent risks such as overcharging and overheating that may accelerate battery aging.

[0003] Currently, most BMS (Battery Management Systems) employ charging strategies based on fixed parameters or with simple temperature compensation. These strategies struggle to dynamically adapt to diverse user needs and complex, ever-changing application environments, easily leading to unnecessary battery life loss and a degraded user experience. Summary of the Invention

[0004] This application provides a charging control method, apparatus, device, storage medium, and program product to achieve deep integration of charging strategies and user behavior, thereby improving user satisfaction, extending battery life, and reducing long-term usage costs.

[0005] In a first aspect, embodiments of this application provide a charging control method, including:

[0006] Obtain the target user profile of the user to which the target battery belongs. The target user profile is constructed based on the historical data of at least one battery, which includes the target battery. The historical data includes at least one of the following: the behavioral data of the user to which the target battery belongs, the environmental data of the environment in which the target battery is located, or the status data.

[0007] Acquire real-time data of the target battery;

[0008] Based on the target user profile and real-time data, the target charging strategy for the target battery is determined. The target charging strategy is used to indicate at least one of the charging current, charging voltage and charging time of the target battery during the charging process.

[0009] Based on the target charging strategy, control the charging of the target battery.

[0010] In this embodiment, user profile-driven charging strategy can dynamically adapt to the user's actual needs, avoiding the low charging efficiency or excessive battery wear caused by traditional fixed parameter strategies. Ultimately, it achieves deep integration of charging strategy and user behavior, improves user satisfaction, and extends battery life.

[0011] In one possible implementation, obtaining the target user profile of the user to whom the target battery belongs includes:

[0012] Obtain historical data for at least one battery;

[0013] Using a pre-defined clustering algorithm and the data features of historical data, classify the users to which at least one battery belongs to obtain at least one user group;

[0014] For any user group, generate at least one user profile for each user in the user group based on the feature vector of the user group and the feature vector of each user in the user group.

[0015] Obtain the target user profile of the user to which the target battery belongs from the user profiles of each user in at least one user group.

[0016] In this embodiment, a clustering algorithm is used to perform multi-dimensional analysis of user historical data, realizing automatic classification and refined profiling of user groups. Through feature vector space modeling, the system can accurately identify different charging behavior patterns and quantify individual differences among users in the group. The charging strategy generated based on this can inherit the common characteristics of the group and can be dynamically adjusted according to the individual deviation, effectively solving the technical problem that traditional single strategies cannot take into account both group patterns and individual differences. This processing mechanism achieves truly personalized charging management while ensuring optimal battery life.

[0017] In one possible implementation, a target charging strategy for the target battery is determined based on the target user profile and real-time data, including:

[0018] Based on the coupling model, the battery life of the target battery under multiple charging strategies is determined. The coupling model includes the equivalent circuit model, thermal model, and battery aging model of the target battery. The equivalent circuit model is used to indicate the electrochemical information of the target battery, the thermal model is used to indicate the temperature change information of the target battery during charging, and the battery aging model is used to indicate the battery capacity decay information of the target battery during charging.

[0019] Based on the objective function and battery life, the charging strategy for the target battery is determined from multiple charging strategies.

[0020] Based on the target user profile and real-time data, the charging strategy for the target battery is adjusted to obtain the target charging strategy for the target battery.

[0021] In this embodiment, a coupled electrochemical-thermal-aging multiphysics model is constructed to achieve precise optimization and personalized adaptation of charging strategies. The system first uses the coupled model to predict battery life degradation under different charging strategies, then optimizes and selects a benchmark strategy through an objective function, and finally dynamically adjusts the benchmark strategy based on user profile characteristics. This model-driven and data-driven approach ensures both the scientific rigor of the charging strategy at the electrochemical level and achieves personalized adaptation at the user level. It effectively solves the technical challenge of the disconnect between battery health management needs and actual user habits, significantly improving user satisfaction while ensuring battery lifespan.

[0022] In one possible implementation, a charging strategy for the target battery is determined from multiple charging strategies based on an objective function and battery life, including:

[0023] Based on the objective function, battery life, and charging cost, determine the function value of the target battery under multiple charging strategies;

[0024] Based on the function values ​​of the target battery under multiple charging strategies, the charging strategy for the target battery is determined from the multiple charging strategies.

[0025] In this embodiment, a comprehensive performance evaluation of charging strategies is achieved by introducing a multi-objective optimization function. Based on coupled model prediction, the system comprehensively considers battery life degradation rate and charging economic indicators to construct a comprehensive evaluation system that includes both technical and economic parameters. By calculating the function evaluation values ​​under different charging strategies, the system can automatically select the charging scheme that achieves the optimal balance between battery life maintenance and usage cost control. This multi-factor decision-making mechanism overcomes the limitations of optimizing a single technical indicator, ensuring that the final generated charging strategy meets both the technical requirements of battery health management and the user's economic needs, thus achieving a unity of technical and economic benefits.

[0026] In one possible implementation, determining the charging strategy for the target battery from multiple charging strategies based on the function values ​​of the target battery under multiple charging strategies includes:

[0027] Based on the function values ​​under multiple charging strategies and the constraints of the target battery, the charging strategy for the target battery is determined from the multiple charging strategies.

[0028] The charging strategy satisfies the following constraints: the constraints include at least one of the following:

[0029] Battery safety conditions include the safe range of at least one of the following: charging voltage, charging current, and battery charging temperature.

[0030] The user's requirements include at least one of the following: the required charging time or the required battery usage time.

[0031] The load constraints of the power grid include the load on the power grid.

[0032] In this embodiment, an optimization decision-making mechanism under multiple constraints is established to ensure the safety and applicability of the charging strategy. Based on a comprehensive evaluation function value, the system introduces triple constraints: battery safety boundary, user needs, and grid load status, to construct a complete optimization decision-making model. This technical solution first ensures that all candidate strategies meet safety thresholds such as battery voltage, current, and temperature. Then, it filters strategies based on the user's expected charging time and usage needs. Finally, it coordinates and optimizes the strategy in conjunction with the real-time grid load status. This multi-constraint optimization architecture effectively solves the balance problem between safety risks, user experience, and grid coordination during the charging strategy formulation process. It prevents safety hazards such as battery overcharging and overheating, ensures that the charging scheme meets the user's actual usage expectations, and smooths grid load fluctuations, achieving a comprehensive optimization goal that unifies safety and reliability, user satisfaction, and grid friendliness.

[0033] In one possible implementation, the method further includes:

[0034] The charging strategy is optimized based on an optimization algorithm to obtain an optimized charging strategy; the optimization algorithm includes at least one of the following:

[0035] Particle swarm optimization algorithm is used to generate charging strategies;

[0036] A module predictive control algorithm is used to dynamically adjust the charging strategy;

[0037] Fuzzy logic control algorithm is used to compensate for the charging strategy.

[0038] In this embodiment, the introduction of an intelligent optimization algorithm significantly enhances the dynamic optimization capability of the charging strategy. The system employs a particle swarm optimization algorithm for multi-parameter space search, rapidly generating a charging curve close to the global optimum; it utilizes a model predictive control algorithm to establish a rolling optimization mechanism, dynamically adjusting charging parameters based on real-time state feedback; and it combines a fuzzy logic control algorithm to handle system nonlinearity and uncertainty, achieving intelligent compensation for the charging process. This hybrid optimization architecture effectively solves the real-time optimization challenge of charging strategies under complex operating conditions, ensuring both the algorithm's global search capability in the solution space and enhancing the system's adaptability and robustness to dynamic changes. Ultimately, it achieves continuous optimization of the charging process under multiple objectives, including safety, efficiency, and economy.

[0039] In one possible implementation, controlling the charging of the target battery based on a target charging strategy includes:

[0040] Acquire charging data from the power grid, including at least one of the following: time-of-use electricity price and predicted load.

[0041] Based on the target user profile and the historical charging data of the target battery, predict the charging demand of the target battery;

[0042] Optimize the target charging strategy based on charging data and charging demand;

[0043] Based on the optimized target charging strategy, control the charging of the target battery.

[0044] In this embodiment, a global optimization of the charging strategy is achieved by introducing a grid interaction and demand forecasting mechanism. The system first acquires time-of-use electricity pricing and load forecasting data from the grid, and then accurately predicts individual charging needs by combining user profiles and historical charging records. Based on this, a multi-objective optimization algorithm is used to collaboratively consider grid status, user demand, and battery health management, dynamically adjusting the timing and power parameters of the charging strategy. This grid-aware charging control method effectively solves the coordination problem between user charging behavior and grid operating status, ensuring timely satisfaction of user charging needs while achieving the dual objectives of economical charging and grid peak shaving and valley filling through electricity price guidance and load regulation, significantly improving the overall energy efficiency and grid coordination capabilities of the charging system.

[0045] In one possible implementation, the method further includes:

[0046] Control the display interface of the target device to display the target charging strategy, and the target battery is the battery of the target device.

[0047] In this embodiment, the introduction of a human-computer interaction mechanism significantly improves the transparency and user participation of charging management. The system visualizes the optimized target charging strategy through the device display interface, specifically displaying information such as charging mode selection, estimated completion time, electricity cost analysis, and impact assessment on battery health. This technical solution effectively solves the information asymmetry problem between users and the battery management system, enabling complex multi-objective optimization results to be conveyed to users in an intuitive and easy-to-understand way. By providing an interactive interface for strategy confirmation or manual adjustment, it ensures users' right to know and choose regarding the charging process while ensuring the smooth execution of the system's optimization strategy. This achieves an effective integration of intelligent algorithm decision-making and user subjective preferences, ultimately enhancing user trust and satisfaction with charging management.

[0048] Secondly, embodiments of this application provide a charging control device, including:

[0049] The first acquisition module is used to acquire the target user profile of the user to which the target battery belongs. The target user profile is constructed based on the historical data of at least one battery, which includes the target battery. The historical data includes at least one of the following: the behavioral data of the user to which the target battery belongs, the environmental data of the environment in which the target battery is located, or the status data.

[0050] The second acquisition module is used to acquire real-time data of the target battery;

[0051] The determination module is used to determine the target charging strategy for the target battery based on the target user profile and real-time data; the target charging strategy is used to indicate at least one of the charging current, charging voltage and charging time of the target battery during the charging process.

[0052] The control module is used to control the charging of the target battery based on the target charging strategy.

[0053] In one possible implementation, the first acquisition module is specifically used for:

[0054] Obtain historical data for at least one battery;

[0055] Using a pre-defined clustering algorithm and the data features of historical data, classify the users to which at least one battery belongs to obtain at least one user group;

[0056] For any user group, generate at least one user profile for each user in the user group based on the feature vector of the user group and the feature vector of each user in the user group.

[0057] Obtain the target user profile of the user to which the target battery belongs from the user profiles of each user in at least one user group.

[0058] In one possible implementation, the determining module is specifically used to: determine the battery life of the target battery under multiple charging strategies based on the coupling model; the coupling model includes an equivalent circuit model, a thermal model, and a battery aging model of the target battery, the equivalent circuit model is used to indicate the electrochemical information of the target battery, the thermal model is used to indicate the temperature change information of the target battery during the charging process, and the battery aging model is used to indicate the battery capacity decay information of the target battery during the charging process.

[0059] Based on the objective function and battery life, the charging strategy for the target battery is determined from multiple charging strategies.

[0060] Based on the target user profile and real-time data, the charging strategy for the target battery is adjusted to obtain the target charging strategy for the target battery.

[0061] In one possible implementation, the determining module is specifically used for:

[0062] Based on the objective function, battery life, and charging cost, determine the function value of the target battery under multiple charging strategies;

[0063] Based on the function values ​​of the target battery under multiple charging strategies, the charging strategy for the target battery is determined from the multiple charging strategies.

[0064] In one possible implementation, the determining module is specifically used for:

[0065] Based on the function values ​​under multiple charging strategies and the constraints of the target battery, the charging strategy for the target battery is determined from the multiple charging strategies.

[0066] The charging strategy satisfies the following constraints: the constraints include at least one of the following:

[0067] Battery safety conditions include the safe range of at least one of the following: charging voltage, charging current, and battery charging temperature.

[0068] The user's requirements include at least one of the following: the required charging time or the required battery usage time.

[0069] The load constraints of the power grid include the load on the power grid.

[0070] In one possible implementation, the charging control device further includes:

[0071] The optimization module is used to optimize the charging strategy based on an optimization algorithm to obtain an optimized charging strategy; the optimization algorithm includes at least one of the following:

[0072] Particle swarm optimization algorithm is used to generate charging strategies;

[0073] A module predictive control algorithm is used to dynamically adjust the charging strategy;

[0074] Fuzzy logic control algorithm is used to compensate for the charging strategy.

[0075] In one possible implementation, the control module is specifically used for:

[0076] Acquire charging data from the power grid, including at least one of the following: time-of-use electricity price and predicted load.

[0077] Based on the target user profile and the historical charging data of the target battery, predict the charging demand of the target battery;

[0078] Optimize the target charging strategy based on charging data and charging demand;

[0079] Based on the optimized target charging strategy, control the charging of the target battery.

[0080] In one possible implementation, the control module is also used for:

[0081] Control the display interface of the target device to display the target charging strategy, and the target battery is the battery of the target device.

[0082] Thirdly, embodiments of this application provide a BMS system, including: a memory and a processor;

[0083] The memory stores the instructions that the computer executes;

[0084] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0085] Fourthly, embodiments of this application provide a vehicle, including: a target battery, and a BMS system as described in the third aspect.

[0086] Fifthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0087] In a sixth aspect, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0088] This application provides a charging control method, apparatus, device, storage medium, and program product. In this method, a personalized user profile is first constructed based on historical data (including user behavior patterns, environmental conditions, and battery status), while simultaneously collecting real-time operating parameters of the target battery. Then, a personalized charging strategy is generated based on the user profile and real-time status data, thereby dynamically adjusting the current, voltage, and time parameters during the charging process based on the charging strategy. This solution achieves deep integration of charging strategy and user behavior, improving user satisfaction while extending battery life and reducing long-term usage costs. Attached Figure Description

[0089] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0090] Figure 1 A schematic diagram illustrating a scenario for the charging control method provided in this application;

[0091] Figure 2 Flowchart of the charging control method provided in this application Figure 1 ;

[0092] Figure 3 Flowchart of the charging control method provided in this application Figure 2 ;

[0093] Figure 4 Flowchart of the charging control method provided in this application Figure 3 ;

[0094] Figure 5 This application provides a schematic diagram of the BMS system architecture.

[0095] Figure 6 A schematic diagram of the charging control device provided in this application;

[0096] Figure 7 A schematic diagram of the BMS system provided in this application;

[0097] Figure 8 A structural schematic diagram of the vehicle provided in this application.

[0098] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0099] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0100] First, let me explain the terms used in this application:

[0101] Battery Management System (BMS)

[0102] State of Charge (SOC)

[0103] State of Health (SOH)

[0104] Vehicle Identification Number (VIN)

[0105] Microcontroller Unit (MCU)

[0106] Global Positioning System (GPS)

[0107] K-means clustering algorithm (K-means)

[0108] Model Predictive Control (MPC)

[0109] Vehicle-to-Grid (V2G) technology

[0110] In related technologies, most BMS systems employ fixed parameters or simple environmental adaptation strategies for charging, failing to fully consider users' personalized charging behaviors. For example, different users exhibit significant differences in factors such as fast charging frequency, initial and final state of charge (SOC), average daily mileage, and charging time preferences, but existing systems cannot provide personalized charging solutions based on these differences. This disconnect results in charging strategies that fail to meet users' actual needs, thus degrading the user experience.

[0111] Figure 1 A schematic diagram illustrating a scenario for the charging control method provided in this application. For example... Figure 1 As shown, the specific application scenario of this application includes a target battery and a BMS system. Its core lies in the BMS system combining user profiles with real-time data to generate a personalized charging strategy for the target battery, thereby achieving dynamic charging control. Specifically, this scenario includes the following stages:

[0112] 1. Input and Construction Phase

[0113] Historical data input: The BMS system acquires long-term operational data from one or more batteries (including the target battery itself), specifically including:

[0114] Behavioral data: Users' charging habits, such as preferred charging times and frequency of choosing between fast and slow charging.

[0115] Environmental data: Historical records of temperature and humidity of the environment in which the battery is located.

[0116] Status data: battery capacity decay history, internal resistance changes, etc.

[0117] Real-time data input: The system synchronously acquires the target battery's instantaneous status parameters before charging begins, such as voltage, temperature, and current state of charge (SOC), to reflect the target battery's real-time health status.

[0118] 2. BMS System Decision-Making Phase

[0119] Based on historical input data, the BMS system constructs a target user profile using data mining and machine learning algorithms (such as cluster analysis). This profile quantifies the user's long-term behavioral patterns and the battery's environmental characteristics. A comprehensive judgment is then made based on the target user profile and real-time data. For example, if the user profile identifies the user as "economical" and real-time data indicates normal battery temperature, the module will generate a charging strategy that prioritizes low cost and battery life. Conversely, if the user profile identifies the user as "efficiency-first," it may generate a charging strategy that is as fast as possible within safe limits. Finally, the module outputs the target charging strategy, which is a specific set of instructions for charging current, charging voltage, and charging time.

[0120] 3. Control Execution Phase

[0121] The BMS strategy decision module transforms the generated target charging strategy into control commands, which directly act on the target battery to control the charger to charge the target battery with specific current, voltage and time.

[0122] In some embodiments, the battery and BMS system can be located in any device, and this application does not limit this. For example, the battery and BMS system can be located in vehicles, consumer electronics devices (such as mobile phones, computers, wearable devices, etc.), and mechanical equipment (such as electric construction machinery, drones, ships, etc.).

[0123] The charging control method provided in this application first constructs a personalized user profile based on historical data (including user behavior patterns, environmental conditions, and battery status), while simultaneously collecting real-time operating parameters of the target battery. Then, a personalized charging strategy is generated based on the user profile and real-time status data, thereby dynamically adjusting the current, voltage, and time parameters during the charging process based on the charging strategy. This solution achieves deep integration of charging strategy and user behavior, improving user satisfaction while extending battery life and reducing long-term usage costs.

[0124] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0125] Figure 2 Flowchart of the charging control method provided in this application Figure 1 The execution entity of this application embodiment is the aforementioned BMS system. For example... Figure 2 As shown, the method includes the following steps:

[0126] S201. Obtain the target user profile of the user to whom the target battery belongs.

[0127] In some embodiments, the target user profile is constructed based on historical data of at least one battery, which includes the target battery.

[0128] In some embodiments, historical data includes at least one of the following: behavioral data of at least one user to whom the battery belongs, environmental data of the environment in which the battery is located, or status data.

[0129] In some embodiments, user behavior data includes at least one of the following key indicators: fast charging frequency, SOC at the start and end of charging, average daily usage time, average daily mileage (vehicle), and charging time preference. The user behavior data is obtained by analyzing historical charging data and driving data.

[0130] In some embodiments, environmental data includes at least one of the following: ambient temperature, humidity, air pressure, etc.

[0131] In some embodiments, the status data includes, but is not limited to, at least one of the following: battery type, nominal capacity, current SOC, SOH, temperature, and other battery status information.

[0132] In some embodiments, the target user profile corresponding to the target battery is obtained from the user profile through the following steps S1-S2:

[0133] S1. Generate target user query vector

[0134] When a target user starts charging, the system immediately extracts data from their most recent period (such as the past week or month). This data is consistent with the feature dimensions used when building the user profile, thereby generating a "query vector Q" that represents the user's recent behavior.

[0135] Recent behavioral data: such as recent fast charging frequency, average starting / ending SOC of charging, and common charging time periods.

[0136] Vehicle identification and status data: vehicle VIN code, current battery SOH, internal resistance, etc.

[0137] S2. Retrieve and match in the image database

[0138] The system calculates the similarity between the query vector Q generated in the previous step and the central feature vectors (C1, C2, ..., CN) of all user groups in the user profile database. The matching process mainly includes, but is not limited to, the following two methods:

[0139] Method 1. Obtain target user profiles based on group matching.

[0140] Similarity calculation: Using algorithms such as cosine similarity and Euclidean distance, the similarity score between the target user's query vector Q and the center vector Ci of each group is calculated.

[0141] Match the most similar group: Select the user group with the highest similarity and use the profile of that group as the base template for the target user profile.

[0142] For example, after calculation, the system finds that the query vector Q of the target user has the highest similarity to the center vector C3 of "Group 3 (high frequency fast charging, short commuting type)". Then the system will assign the common features of "Group 3" (such as: it is recommended to fast charge between 20% and 80% of battery SOC) to the target user, thereby obtaining the target user profile corresponding to the target battery.

[0143] Method 2. Obtain target user profiles through precise matching based on individual profiles.

[0144] If the system maintains an independent, dynamically updated personalized profile file for each user, the matching process will be more direct, retrieving the target user profile based on key identifiers. For example, the system can directly use the target's unique identifier (such as the vehicle VIN or user account ID) as the primary key, execute a query in the user profile database, and directly retrieve and call the latest user profile bound to that VIN or user ID as the user profile for that target battery.

[0145] S202, Obtain real-time data of the target battery.

[0146] In some embodiments, the real-time data of the target battery includes, but is not limited to, at least one of the following:

[0147] Electrical data: such as voltage (real-time voltage, single-core voltage), etc.

[0148] Current data: Real-time charging / discharging current.

[0149] State of Charge (SOC): The current percentage of remaining battery power.

[0150] Thermal status data: Temperature data, including the temperature of multiple key points within the battery pack (such as maximum temperature, minimum temperature, and average temperature).

[0151] Health and safety data: State of health (SOH), such as the percentage of the current maximum usable capacity of the battery relative to the factory rated capacity.

[0152] Resistance data: such as the battery's internal impedance, insulation resistance, etc.

[0153] In some embodiments, acquiring real-time data of the target battery includes the following steps S3-S6:

[0154] S3. Signal Acquisition: The raw electrical signals of the battery pack and individual cells are continuously acquired through a high-precision voltage sampling circuit, current sensor (such as a Hall sensor), and temperature sensor (such as a thermistor).

[0155] S4. Data Processing: The main control chip (MCU) of the BMS performs filtering (removing electromagnetic interference noise), calibration (compensating for sensor errors), and linearization on the raw signal.

[0156] S5. State Calculation: Based on the processed clean data, the State of Charge (SOC) is estimated in real time using a specific algorithm (such as the ampere-hour integration method combined with the open-circuit voltage method), and the State of Harm (SOH) may be assessed based on long-term data trends.

[0157] S6. Data Output: Finally, the BMS will package and output a standardized real-time data set containing all the above key parameters, waiting for subsequent steps (S203) to call it for joint decision-making with user profiles.

[0158] S203. Determine the target charging strategy for the target battery based on the target user profile and real-time data.

[0159] In some embodiments, the target charging strategy is used to indicate at least one of the charging current, charging voltage, and charging time of the target battery during the charging process.

[0160] The following are some methods for determining the target charging strategy corresponding to user profiles:

[0161] 1. "Efficiency-First" User Profile

[0162] User profile input: For "efficiency-first" users, a high allowable current is recommended; for "battery maintenance" users, a medium or low current is recommended.

[0163] Real-time data calibration: The system reads the battery's real-time temperature and current SOC. If the temperature exceeds the safety threshold, or at low temperatures, the "efficiency priority" request is ignored, and the current is forcibly reduced to a safe range. If the SOC is very low and the temperature is suitable, a high current as per the profile allows is permitted.

[0164] Strategy output: The final instruction is clearly defined as "Constant current stage charging current: 150A (0.5C)".

[0165] Set charging voltage / stop SOC (determines the charging cut-off point and battery stress).

[0166] 2. "Short-distance commuter" user profile

[0167] User profile input: For "short commuting" users, the recommended charging stop SOC is 80%; for "long-distance preparation" users, charging to 95% or 100% is allowed.

[0168] Real-time data calibration: The system reads the battery's State of Health (SOH). If the SOH indicates that the battery has aged significantly, the full charge voltage will be further reduced (e.g., from 4.2V to 4.15V) based on the user profile recommendations to alleviate battery stress.

[0169] Strategy output: The final instruction is clearly defined as "Charging termination condition: voltage reaches 4.15V, or SOC reaches 95%".

[0170] 3. "Economy-conscious" user profile

[0171] User profile input: For the "Economy" user profile, it is strongly recommended to set the charging start time to off-peak electricity prices (such as after 11 pm).

[0172] Real-time data calibration: The system reads the current SOC and the user-preset next usage time. If the current SOC is extremely low and may not be able to support the vehicle until off-peak hours, it is recommended to charge immediately to a safe level (e.g., 30%). The system will calculate and ensure that charging is completed before the usage time based on the target SOC and the set current.

[0173] Strategy output: The final instruction is clearly stated as "Planned charging period: starting at 23:30 that night, expected to be completed before 06:00 the next day".

[0174] S204. Control the charging of the target battery based on the target charging strategy.

[0175] In some embodiments, the BMS dynamically communicates with the charger based on real-time feedback from the battery (e.g., temperature rise, voltage reaching a stage threshold) to fine-tune output parameters, thereby controlling the charging of the target battery. For example, the strategy might be "to charge at a constant current of 100A until the voltage reaches 4.0V." When the BMS detects that the voltage has reached 4.0V, it immediately instructs the charger to switch to the next stage of "constant voltage 4.0V charging, with gradually decreasing current."

[0176] Specifically, the BMS sends the determined "target charging strategy" (including specific charging current, voltage, time and other parameters) to the charging device through a communication protocol, so that the charging device can accurately output electrical energy according to the voltage and current specified by the strategy to charge the target battery.

[0177] The charging control method provided in this application first constructs a personalized user profile based on historical data (including user behavior patterns, environmental conditions, and battery status), while simultaneously collecting real-time operating parameters of the target battery. Then, a personalized charging strategy is generated based on the user profile and real-time status data, thereby dynamically adjusting the current, voltage, and time parameters during the charging process based on the charging strategy. This solution achieves deep integration of charging strategy and user behavior, improving user satisfaction while extending battery life and reducing long-term usage costs.

[0178] Figure 3 Flowchart of the charging control method provided in this application Figure 2 .like Figure 3 As shown, in this embodiment... Figure 2 Based on the illustrated embodiment, the charging control method will be described in detail, which includes the following steps:

[0179] S301. Obtain historical data for at least one battery.

[0180] Specifically, acquiring historical data for at least one battery includes the following steps:

[0181] S1. Data Acquisition and Preprocessing

[0182] First, at least one of the following is collected through sensors and cloud servers: user behavior data, environmental data, or status data of the battery's environment. For example, for vehicle batteries, onboard sensors / BMS directly collect real-time streaming data such as voltage, current, temperature, and SOC. The vehicle controller / cloud server records user actions (such as charging start / end time, charging settings), driving trajectory (average daily mileage), and ambient temperature data obtained through GPS and the network.

[0183] Furthermore, the collected data undergoes cleaning and standardization to remove outliers and noise. For example, outlier removal includes identifying and eliminating instantaneous current maxima or temperature minima caused by sensor malfunctions; and data smoothing and noise reduction involves using filtering algorithms (such as Kalman filtering) to smooth data curves and remove random interference.

[0184] Finally, missing data is filled by interpolation or based on similar users. For example, for a small number of missing data points, interpolation can be used to fill in the gaps; for large missing segments, "similar users" with similar behavioral patterns can be found and their data can be used to fill in the gaps.

[0185] S2. Feature Extraction and Analysis

[0186] In some embodiments, feature extraction includes, but is not limited to, the following:

[0187] Fast charging frequency: Number of fast charging cycles / Total number of charging cycles.

[0188] Average Start / End SOC: Reflects the user's battery usage depth and charging habits. For example, a user who always charges from 50% to 100% experiences different battery stress compared to a user who charges from 20% to 80%.

[0189] Average daily mileage: Determines whether the user is a long-distance or short-distance commuter.

[0190] Common charging time periods: Identify whether the user is a "nighttime charging type", "daytime work charging type", or "random charging type".

[0191] Environmental feature extraction (quantification of "vehicle usage environment"): Analyze the average ambient temperature and temperature difference in the user's usual residence area, as well as charging behavior preferences in different temperature ranges (such as <0°C, 0-25°C, >35°C) (such as whether they will actively choose slow charging on hot days).

[0192] State feature extraction (quantification of "vehicle condition"): For example, static parameters: battery type, nominal capacity. These are inherent attributes of the vehicle; dynamic health parameters: current SOH (state of health, reflecting capacity decay), internal resistance (reflecting the degree of battery aging). These parameters determine whether the battery can withstand certain aggressive charging strategies.

[0193] S302. Using a preset clustering algorithm and the data features of historical data, classify the users to which at least one battery belongs to obtain at least one user group.

[0194] In some embodiments, the preset clustering algorithm is, for example, K-means or hierarchical clustering. When using the K-means algorithm, the system projects the feature vectors of all users into a high-dimensional space and finds K centroids (i.e., cluster centers) through iterative calculation, such that the sum of the distances from all user points to their respective centroids is minimized.

[0195] When using hierarchical clustering algorithms, a tree-like clustering structure can be formed, which facilitates the exploration of user groups at different granularities (from coarse to fine).

[0196] S3, Obtain K user groups

[0197] For example: Group A (“Economic Maintenance Type”): characterized by [low fast charging frequency, charging SOC range of 50%-90%, charging at night, and short average daily mileage].

[0198] Group B ("Efficiency-First Type"): Characterized by [high-frequency fast charging, charging SOC range of 20%-100%, random charging time, and long average daily mileage].

[0199] Group C (“Cautious Users in High-Temperature Areas”): Characterized by [frequent exposure to high-temperature environments and proactive reduction of fast charging frequency under high temperatures].

[0200] S303. For any user group, generate at least one user profile for each user in the user group based on the feature vector of the user group and the feature vector of each user in the user group.

[0201] In some embodiments, the feature vector is, for example, behavioral features, environmental features, and state features.

[0202] Generate user profiles for each user, including:

[0203] 1. Establish group feature vectors, where each user group has a central feature vector that represents the "typical image" of the group.

[0204] 2. An individual's user profile is jointly determined by the central feature vector of their group and their own feature vector. Specifically, the profile not only includes the label "this user belongs to group A," but also quantitative information about "this user's specific location within group A." For example, by calculating the Euclidean distance or cosine similarity between the individual's vector and the group's central vector, it can be determined whether the user is a "typical member" or a "marginal member" of the group. For instance, if a user in an "economical maintenance" group has a slightly higher "fast charging frequency" than the group's central value, their profile will include this subtle difference. When formulating strategies for them, the system might allow them to perform a one-time fast charge in unconventional situations (such as urgent need for a vehicle).

[0205] S304. Obtain the target user profile of the user to which the target battery belongs from the user profiles of each user in at least one user group.

[0206] In some embodiments, when a charging strategy needs to be formulated for the target battery, the system executes step S304. Specifically, the system extracts the real-time data of the target user (i.e., the real-time data obtained in S202) and generates its temporary feature vector; it calculates the similarity between this temporary vector and the central feature vectors of all user groups to find the user group with the highest similarity; from this group, it retrieves and calls the personalized user profile previously generated and stored for this target user (through its unique VIN code or user identifier).

[0207] Figure 4 Flowchart of the charging control method provided in this application Figure 3 .like Figure 4 As shown, in this embodiment... Figure 2 Based on the illustrated embodiment, the charging control method will be described in detail, which includes the following steps:

[0208] S401. Obtain the target user profile of the user to whom the target battery belongs.

[0209] In some embodiments, the target user profile is constructed based on historical data of at least one battery, which includes the target battery.

[0210] In some embodiments, historical data includes at least one of the following: behavioral data of at least one user to whom the battery belongs, environmental data of the environment in which the battery is located, or status data.

[0211] S402, Obtain real-time data of the target battery.

[0212] It should be noted that steps S401-S402 are the same as... Figure 2 Steps S201-S202 in the illustrated embodiment are similar, and can be referred to the above embodiment for details, which will not be repeated here.

[0213] S403. Based on the coupling model, determine the battery life of the target battery under multiple charging strategies.

[0214] In some embodiments, the coupling model (electro-thermal-aging coupling model) includes the equivalent circuit model, thermal model, and battery aging model of the target battery.

[0215] Among them, the equivalent circuit model is used to indicate the electrochemical information of the target battery; for example, circuit elements such as resistors and capacitors are used to simulate the dynamic characteristics of the battery (such as ohmic internal resistance and polarization effect), which can accurately predict the changes in battery terminal voltage and SOC under different charging current / voltage.

[0216] Thermal models are used to indicate the temperature changes of a target battery during charging; for example, they describe the heat generation (Joule heating, reaction heating) and heat dissipation (convection, conduction) processes of the battery during charging, and predict the temperature changes of the battery.

[0217] Battery aging models are used to indicate the battery capacity decay information of a target battery during the charging process; for example, to quantify the accelerating effect of different stresses (such as high SOC, high current, high temperature) on battery capacity decay (SOH decrease) and internal resistance increase.

[0218] The three models in the coupled model are linked in real time. For example, a large current (electrical model) will lead to increased heat generation (thermal model), and the increase in temperature (thermal model) will accelerate capacity decay (aging model).

[0219] In some embodiments, the coupling model, when determining the battery life of a target battery under multiple charging strategies, includes the following steps:

[0220] For any charging strategy (e.g., "charge at 150A for 30 minutes"), a coupled model is used for simulation. For example, the electrical model calculates the battery voltage and heat generation at this current; the thermal model calculates the real-time battery temperature based on the heat generation; and the aging model calculates the battery capacity degradation during this process using a preset mathematical formula based on the voltage and current output by the electrical model and the temperature output by the thermal model. Finally, the battery life under this charging strategy is determined based on the battery capacity degradation.

[0221] In predicting battery life, a cycle life prediction model can be used. For example, a cycle life prediction model can be established using the Arrhenius equation and the current-accelerated aging coefficient to quantify the impact of different charging strategies on battery life.

[0222]

[0223] in, For battery life, Let A be the capacity decay rate, and A be the pre-exponential factor. R is the activation energy, T is the gas constant, I is the absolute temperature, Ah is the charging current, and B and C are model parameters.

[0224] S404. Based on the objective function and battery life, determine the charging strategy for the target battery from multiple charging strategies.

[0225] Specifically, the system searches among multiple charging strategies (different current curves), predicts the battery life and charging cost of each strategy through a coupled model, calculates the function value of each strategy, and finally selects the strategy with the smallest function value (i.e., the overall optimal strategy) as the benchmark charging strategy.

[0226] In some embodiments, S404 specifically includes the following steps S4041-S4042:

[0227] S4041. Determine the function value of the target battery under multiple charging strategies based on the objective function, battery life, and charging cost.

[0228] In some embodiments, the objective function is, for example, Where F is the overall target value, L is the battery life, and Cost is the charging cost. and These are the weighting coefficients.

[0229] The charging cost is calculated based on the electricity price corresponding to the charging amount and charging time of the charging strategy (e.g., a cost of 2.5 yuan). The weighting coefficients (w1, w2) represent the user's preference between "extending battery life" and "saving on electricity costs." For example, if w1 > w2, the system is more inclined to protect the battery; if w2 > w1, the system is more inclined to save on charging costs.

[0230] In some embodiments, the weights may be preset by the system or obtained directly from the user profile (e.g., setting a higher w2 for "economic" users).

[0231] S4042. Based on the function values ​​of the target battery under multiple charging strategies, determine the charging strategy of the target battery from the multiple charging strategies.

[0232] In some embodiments, the smaller the F value, the better the overall performance of the strategy in terms of "lifetime" and "cost". The charging strategy with the smallest function value F can be directly selected as the target charging strategy.

[0233] In some embodiments, the charging strategy for the target battery can be determined from multiple charging strategies based on the function values ​​under multiple charging strategies and the constraints of the target battery.

[0234] The charging strategy satisfies the following constraints: the constraints include at least one of the following:

[0235] Battery safety conditions include the safe range of at least one of the following: charging voltage, charging current, and battery charging temperature.

[0236] The user's requirements include at least one of the following: the required charging time or the required battery usage time.

[0237] The load constraints of the power grid include the load on the power grid.

[0238] Specifically, based on the function values ​​under multiple charging strategies and the constraints of the target battery, the charging strategy for the target battery is determined from the multiple charging strategies, including the following steps:

[0239] Step 1: Eliminate all candidate strategies that do not meet the hard constraints.

[0240] For example, eliminate all strategies that "exceed the 4.2V safety limit for charging voltage".

[0241] For example, eliminate all strategies that "cannot be completed within the user's requested 8-hour usage period".

[0242] Step 2: Among all the remaining feasible strategies that satisfy the constraints, select the one with the smallest function value F as the charging strategy for the target battery.

[0243] S405. Based on the target user profile and real-time data, adjust the charging strategy of the target battery to obtain the charging strategy of the target battery.

[0244] In some embodiments, the charging strategy for the target battery is adjusted, including but not limited to at least one of the following dimensions:

[0245] 1. Charging current / power adjustment

[0246] For example, efficiency-first users tend to maintain or accept higher charging currents; battery maintenance-oriented users tend to lower charging currents, even at the cost of some time. If the battery temperature is too high / low, the charging current is forcibly reduced to prioritize safety and lifespan; if the current state of harmlessness (SOH) is low (poor battery health), the current is appropriately reduced to alleviate battery stress. During adjustments, a scaling factor or absolute upper limit can be applied to the current curve of the baseline strategy. For instance, for "efficiency-first" users with normal temperatures, 100% of the baseline strategy current or the maximum permissible safe current is used; for "maintenance-oriented" users or users with "high battery temperature," the current is reduced to 80% of the baseline strategy.

[0247] 2. Adjustment of charging termination conditions

[0248] For example, for short-distance commuting, it is recommended to lower the charging termination SOC (e.g., 80%) to avoid prolonged periods of full charge and significantly extend battery life. For long-distance travel preparations, charging to 95% or 100% SOC is permitted. If the user manually sets the target SOC for this charge, the user's setting will apply. Adjustments can override or modify the target SOC or termination voltage in the baseline strategy. For the default scenario (short-distance users), the charging termination condition is SOC ≥ 80%; for special needs (long-distance travel), the charging termination condition is SOC ≥ 100%.

[0249] 3. Charging sequence adjustment

[0250] For example, for economy users, it is recommended to postpone the start time of charging until the off-peak electricity price period; for regular charging users, calculate the optimal start time to ensure that the car is fully charged just before use, rather than charging continuously. If the current SOC is extremely low (<15%), it may be necessary to start charging immediately to meet basic travel needs; if the user has a preset time for next use, calculate the charging time required and arrange the charging plan accordingly. When adjusting, the start and end times of charging can be rescheduled. For example, for "economy" users with SOC > 30%, adjust to start charging at 23:00 that night (lowest cost); for "extremely low SOC" or "urgent need for use", adjust to start charging immediately.

[0251] S406. Optimize the charging strategy based on the optimization algorithm to obtain the optimized charging strategy.

[0252] In some embodiments, the optimization algorithm includes at least one of the following:

[0253] Particle swarm optimization (PSO) is used to generate charging strategies to solve discrete charging current optimization problems. For example, each possible charging curve is regarded as a "particle". The particles move and search in the solution space by tracking the current best solution and their own historical best solutions, and eventually gather near the best solution.

[0254] The Module Predictive Control (MPC) algorithm is used to dynamically adjust the charging strategy. In the dynamic process, based on the current state and the prediction model, it solves an optimal control problem in a finite time domain in a rolling manner, and only implements the first control step, and then repeats the process in the next cycle.

[0255] Fuzzy logic control algorithms are used to compensate for charging strategies, thereby handling the nonlinearity and uncertainty inherent in battery systems. Precise models cannot accurately describe all situations. They transform experience (such as "if the temperature is high, then appropriately reduce the current") into fuzzy rules that can be executed by a computer, handling complex situations that cannot be described by precise mathematical models. For example, precise input (such as "the current temperature is 38°C") is transformed into fuzzy concepts (such as "the temperature is too high").

[0256] S407. Control the charging of the target battery based on the target charging strategy.

[0257] S408. Obtain charging data from the power grid, including at least one of the power grid's time-of-use electricity price and predicted load.

[0258] Specifically, the system obtains time-of-use electricity prices and load forecast data of the power grid through communication interfaces (such as 4G / 5G modules and Ethernet), and analyzes the peak and valley characteristics of the power grid load curve and the electricity price change pattern to obtain the power grid charging data.

[0259] Time-of-use pricing, for example, is a precise real-time electricity price curve for the next 24 hours or longer, distinguishing between peak, off-peak, and valley periods and their corresponding prices. Load forecasting data, for example, is future load forecasting data obtained from the local distribution network or regional power grid, identifying when the grid experiences excessive pressure (peak load) or has sufficient capacity (valley load).

[0260] S409. Based on the target user profile and the historical charging data of the target battery, predict the charging demand of the target battery.

[0261] In some embodiments, data is first input into a predictive model to predict the charging needs of the target battery. The inputs to the predictive model include: a target user profile, such as the user's long-term behavioral patterns (e.g., when they typically finish using the vehicle and when they begin their next use).

[0262] Historical charging data of the target battery, such as the start and end points of the SOC during historical charging, charging frequency, etc.

[0263] Real-time data, such as the current battery SOC.

[0264] User calendar / navigation information (if authorized), such as whether the user has a long trip planned for the next day.

[0265] The output of the predictive model includes: predicting the user's next car usage time and expected departure SOC (e.g., the user typically wants to depart with 90% battery).

[0266] Furthermore, based on the target SOC, current SOC, and battery capacity, the required charging capacity (kWh) is calculated and combined with the predicted charging cutoff time to define the "charging demand" for this operation.

[0267] S410: Optimize the target charging strategy based on charging data and charging demand.

[0268] In some embodiments, the system evaluates the total charging cost and grid compatibility of each option, and selects the option with the lowest total cost that meets the vehicle usage time requirements as the final optimization strategy.

[0269] S411. Based on the optimized target charging strategy, control the charging of the target battery.

[0270] S412, Control the display interface of the target device to display the target charging strategy.

[0271] In some embodiments, the target battery is the battery of the target device. For example, if the target device is a vehicle, then the target battery is the battery in the vehicle.

[0272] Specifically, the system generates an easy-to-understand graphical interface, displayed on the vehicle's central control screen or a mobile phone. The displayed target charging strategy typically includes at least one of the following:

[0273] Charging plans, for example, can be displayed as a timeline showing the start and end times of a planned charge.

[0274] Economic information, such as the estimated total cost of charging, is compared with the cost of "Charge Now" to show the amount of savings.

[0275] Battery maintenance information, such as the benefits of the current strategy for battery life (e.g., "We have set an 80% charge limit for you to protect the battery").

[0276] Grid coordination prompts, such as, “Schedule your charging for the early morning to support the green grid.”

[0277] In some embodiments, the display interface may also provide options for confirmation or manual operation. For example, if a user urgently needs a vehicle, they can select "Full Charge Now," and the system will respect the user's choice and temporarily abandon the optimization strategy.

[0278] It should be noted that any one or more steps in steps S408-S412 are optional steps.

[0279] In some embodiments, the present application can achieve global optimization of the charging strategy by interacting with grid load data, for example,

[0280] 1. Load Forecasting and Scheduling: Based on user profiles and historical charging data, predict user charging demand and combine it with grid load forecasting data to generate grid-friendly charging plans.

[0281] 2. Adjust charging time and power according to the power grid's time-of-use pricing policy to reduce users' charging costs and smooth the power grid load curve.

[0282] 3. V2G support: Provides charging and discharging coordination optimization strategies for vehicles with V2G capabilities, enabling them to discharge in reverse when the grid needs it, thereby improving grid stability and renewable energy absorption capacity.

[0283] The power grid collaborative optimization mechanism provided in this embodiment can effectively mitigate the impact of charging on the power grid, improve energy utilization efficiency, and promote the deep integration of transportation electrification and the energy internet.

[0284] Figure 5 This is a schematic diagram of the BMS system architecture provided in this application. Figure 5 As shown, the BMS system provided in this embodiment includes: an application layer, an algorithm layer, and a low-level driver layer.

[0285] The underlying driver layer includes:

[0286] The hardware abstraction layer provides a unified hardware access interface, shielding hardware differences.

[0287] Communication interface: Used to enable communication with battery sensors, chargers and external systems.

[0288] The algorithm layer includes:

[0289] User profile module: used to build and update user profiles;

[0290] Battery model module: used to implement the electro-thermal-aging coupled model and related algorithms;

[0291] Optimization algorithm module: Used to implement charging strategy optimization algorithms;

[0292] Control strategy module: Used to implement real-time control of the charging process.

[0293] The application layer includes:

[0294] Human-computer interaction interface: The interface used to provide users with settings and view charging strategies.

[0295] System monitoring: Used to monitor battery status and charging process, providing anomaly handling and alarm functions.

[0296] Data analysis and optimization: Used to continuously optimize models and algorithms based on historical charging data.

[0297] Figure 6 A schematic diagram of the charging control device provided in this application is shown below. Figure 6 As shown, the charging control device 600 provided in this embodiment includes:

[0298] The first acquisition module 601 is used to acquire the target user profile of the user to which the target battery belongs. The target user profile is constructed based on the historical data of at least one battery, which includes the target battery. The historical data includes at least one of the behavioral data of the user to which the at least one battery belongs, environmental data of the environment in which the user is located, or status data.

[0299] The second acquisition module 602 is used to acquire real-time data of the target battery;

[0300] The determination module 603 is used to determine the target charging strategy for the target battery based on the target user profile and real-time data; the target charging strategy is used to indicate at least one of the charging current, charging voltage and charging time of the target battery during the charging process.

[0301] The control module 604 is used to control the charging of the target battery based on the target charging strategy.

[0302] In one possible implementation, the first acquisition module is specifically used for:

[0303] Obtain historical data for at least one battery;

[0304] Using a pre-defined clustering algorithm and the data features of historical data, classify the users to which at least one battery belongs to obtain at least one user group;

[0305] For any user group, generate at least one user profile for each user in the user group based on the feature vector of the user group and the feature vector of each user in the user group.

[0306] Obtain the target user profile of the user to which the target battery belongs from the user profiles of each user in at least one user group.

[0307] In one possible implementation, the determining module 603 is specifically used to: determine the battery life of the target battery under multiple charging strategies based on the coupling model; the coupling model includes an equivalent circuit model, a thermal model, and a battery aging model of the target battery, the equivalent circuit model is used to indicate the electrochemical information of the target battery, the thermal model is used to indicate the temperature change information of the target battery during the charging process, and the battery aging model is used to indicate the battery capacity decay information of the target battery during the charging process.

[0308] Based on the objective function and battery life, the charging strategy for the target battery is determined from multiple charging strategies.

[0309] Based on the target user profile and real-time data, the charging strategy for the target battery is adjusted to obtain the target charging strategy for the target battery.

[0310] In one possible implementation, the determining module is specifically used for:

[0311] Based on the objective function, battery life, and charging cost, determine the function value of the target battery under multiple charging strategies;

[0312] Based on the function values ​​of the target battery under multiple charging strategies, the charging strategy for the target battery is determined from the multiple charging strategies.

[0313] In one possible implementation, the determining module 603 is specifically used for:

[0314] Based on the function values ​​under multiple charging strategies and the constraints of the target battery, the charging strategy for the target battery is determined from the multiple charging strategies.

[0315] The charging strategy satisfies the following constraints: the constraints include at least one of the following:

[0316] Battery safety conditions include the safe range of at least one of the following: charging voltage, charging current, and battery charging temperature.

[0317] The user's requirements include at least one of the following: the required charging time or the required battery usage time.

[0318] The load constraints of the power grid include the load on the power grid.

[0319] In one possible implementation, the charging control device 600 further includes:

[0320] Optimization module 605 is used to optimize the charging strategy based on an optimization algorithm to obtain an optimized charging strategy; the optimization algorithm includes at least one of the following:

[0321] Particle swarm optimization algorithm is used to generate charging strategies;

[0322] A module predictive control algorithm is used to dynamically adjust the charging strategy;

[0323] Fuzzy logic control algorithm is used to compensate for the charging strategy.

[0324] In one possible implementation, the control module 604 is specifically used for:

[0325] Acquire charging data from the power grid, including at least one of the following: time-of-use electricity price and predicted load.

[0326] Based on the target user profile and the historical charging data of the target battery, predict the charging demand of the target battery;

[0327] Optimize the target charging strategy based on charging data and charging demand;

[0328] Based on the optimized target charging strategy, control the charging of the target battery.

[0329] In one possible implementation, the control module 604 is further configured to:

[0330] Control the display interface of the target device to display the target charging strategy, and the target battery is the battery of the target device.

[0331] The charging control device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0332] Figure 7 This is a schematic diagram of the BMS system provided in this application. Figure 7 As shown, the BMS system 700 provided in this embodiment includes at least one processor 701 and a memory 702. Optionally, the BMS system 700 further includes a communication component 703. The processor 701, memory 702, and communication component 703 are connected via a bus 704.

[0333] In a specific implementation, at least one processor 701 executes computer execution instructions stored in memory 702, causing at least one processor 701 to perform the above-described method.

[0334] The specific implementation process of processor 701 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0335] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0336] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0337] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0338] Figure 8 This is a structural diagram of the vehicle provided in this application. Figure 8 As shown, the vehicle 800 includes: a target battery, and Figure 7 The BMS system in China.

[0339] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0340] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0341] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0342] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0343] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0344] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0345] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0346] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0347] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0348] Finally, it should be noted that other embodiments of this application will readily conceive of by those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and alterations may be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A charging control method, characterized in that, include: Obtain a target user profile of the user to which the target battery belongs. The target user profile is constructed based on historical data of at least one battery, including the target battery. The historical data includes at least one of the behavioral data of the user to which the at least one battery belongs, environmental data of the environment in which the user is located, or status data. Obtain real-time data of the target battery; Based on the target user profile and the real-time data, a target charging strategy for the target battery is determined. The target charging strategy is used to indicate at least one of the charging current, charging voltage, and charging time of the target battery during the charging process. Based on the target charging strategy, control the charging of the target battery.

2. The method according to claim 1, characterized in that, The process of obtaining the target user profile of the user to whom the target battery belongs includes: Obtain historical data of the at least one battery; Using a preset clustering algorithm and the data features of the historical data, the users to which the at least one battery belongs are classified to obtain at least one user group; For any user group, a user profile of each user in the at least one user group is generated based on the feature vector of the user group and the feature vector of each user in the user group. Obtain the target user profile of the user to which the target battery belongs from the user profiles of each user in the at least one user group.

3. The method according to claim 1, characterized in that, The step of determining the target charging strategy for the target battery based on the target user profile and the real-time data includes: Based on the coupling model, the battery life of the target battery under multiple charging strategies is determined; the coupling model includes the equivalent circuit model, thermal model, and battery aging model of the target battery. The equivalent circuit model is used to indicate the electrochemical information of the target battery, the thermal model is used to indicate the temperature change information of the target battery during charging, and the battery aging model is used to indicate the battery capacity decay information of the target battery during charging. Based on the objective function and the battery life, determine the charging strategy for the target battery from the plurality of charging strategies; Based on the target user profile and the real-time data, the charging strategy of the target battery is adjusted to obtain the target charging strategy of the target battery.

4. The method according to claim 3, characterized in that, The step of determining the charging strategy for the target battery from the plurality of charging strategies based on the objective function and the battery life includes: Based on the objective function, the battery life, and the charging cost, determine the function value of the target battery under the multiple charging strategies; Based on the function value of the target battery under the multiple charging strategies, the charging strategy of the target battery is determined from the multiple charging strategies.

5. The method according to claim 4, characterized in that, The step of determining the charging strategy for the target battery from the plurality of charging strategies based on the function value of the target battery under the plurality of charging strategies includes: Based on the function values ​​under the multiple charging strategies and the constraints of the target battery, the charging strategy for the target battery is determined from the multiple charging strategies. The charging strategy satisfies the constraints; the constraints include at least one of the following: Battery safety conditions include the safe range of at least one of the following: charging voltage, charging current, and battery charging temperature. The user's requirements include at least one of the following: the required charging time or the required battery usage time. The load constraints of the power grid include the load of the power grid.

6. The method according to claim 5, characterized in that, Also includes: The charging strategy is optimized based on an optimization algorithm to obtain the optimized charging strategy; the optimization algorithm includes at least one of the following: A particle swarm optimization algorithm is used to generate the charging strategy; A module predictive control algorithm is used to dynamically adjust the charging strategy; A fuzzy logic control algorithm is used to compensate for the charging strategy.

7. The method according to claim 1, characterized in that, The step of controlling the charging of the target battery based on the target charging strategy includes: Acquire charging data from the power grid, the charging data including at least one of the power grid's time-of-use electricity price and predicted load; Based on the target user profile and the historical charging data of the target battery, predict the charging demand of the target battery; Based on the charging data and the charging demand, optimize the target charging strategy; Based on the optimized target charging strategy, the target battery is controlled to charge.

8. The method according to any one of claims 1-7, characterized in that, Also includes: The display interface of the target device is controlled to display the target charging strategy, and the target battery is the battery of the target device.

9. A charging control device, characterized in that, include: The first acquisition module is used to acquire a target user profile of the user to which the target battery belongs. The target user profile is constructed based on the historical data of at least one battery, including the target battery. The historical data includes at least one of the behavioral data of the user to which the at least one battery belongs, environmental data of the environment in which the user is located, or status data. The second acquisition module is used to acquire real-time data of the target battery; The determination module is used to determine the target charging strategy for the target battery based on the target user profile and the real-time data. The target charging strategy is used to indicate at least one of the charging current, charging voltage and charging time of the target battery during the charging process; The control module is used to control the charging of the target battery based on the target charging strategy.

10. A battery management system (BMS), characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-8.

11. A vehicle, characterized in that, include: The target battery, and the BMS system as claimed in claim 10.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-8.

13. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-8.

Images